yGT ESTIMATION DEVICE, yGT ESTIMATION METHOD, AND COMPUTER PROGRAM

Abstract

Conventionally, a needle or the like needs to inserted into skin of a subject to invasively collect blood in γGT measurement, which causes a psychological or physical burden on a subject. According to the present invention, it is possible to invasively estimate γGT based on attribute information and non-invasive biological information of a predetermined user by generating a γGT estimation model by machine learning based on attribute information, non-invasive biological information, and blood examination data acquired from a plurality of subjects in advance.

1 . A γGT estimation device comprising:
 an information acquisition unit configured to acquire attribute information and non-invasive biological information of a predetermined user; 
 an estimation model storage unit configured to store a γGT estimation model; and 
 an estimation processing unit configured to calculate a γGT estimated value of the predetermined user based on the attribute information and/or the non-invasive biological information of the predetermined user by using the γGT estimation model. 
 
     
     
         2 . The γGT estimation device according to  claim 1 ,
 wherein the attribute information includes any one or a combination of age and sex, and 
 wherein the non-invasive biological information includes any one or a combination of BMI, blood pressure, pulse wave data, electrocardiogram data, and biological impedance. 
 
     
     
         3 . The γGT estimation device according to  claim 1 , further comprising:
 a training data storage unit configured to store a training data set; and 
 a learning processing unit configured to generate the γGT estimation model by machine learning based on the training data set. 
 
     
     
         4 . The γGT estimation device according to  claim 3 , wherein the training data set includes attribute information, non-invasive biological information, and a blood-measured γGT measured value of a subject. 
     
     
         5 . The γGT estimation device according to  claim 4 , wherein the non-invasive biological information further includes oxygen saturation (SpO2). 
     
     
         6 . The γGT estimation device according to  claim 4 , wherein a coefficient of correlation between a logarithm of the γGT estimated value and a logarithm of the γGT measured value is equal to or larger than 0.6. 
     
     
         7 . The γGT estimation device according to  claim 3 ,
 wherein the training data set includes non-invasive biological information and a blood-measured γGT measured value of a subject, and 
 wherein the estimation processing unit calculates a γGT risk estimated value in place of the γGT estimated value. 
 
     
     
         8 . The γGT estimation device according to  claim 7 ,
 wherein the learning processing unit provides labels indicating existence of the γGT risk to the training data set based on the blood-measured γGT measured value, and 
 wherein, when a difference between the numbers of pieces of data with the γGT risk and data without the γGT risk among the labels is equal to or larger than a predetermined value, the learning processing unit increases the number of pieces of sample data in the training data set to reduce the difference. 
 
     
     
         9 . The γGT estimation device according to  claim 7 ,
 wherein the learning processing unit generates a first γGT risk estimation model and a second γGT risk estimation model by machine learning based on each of training data sets of different kinds, and 
 wherein the estimation processing unit calculates the γGT risk estimated value of the predetermined user by using the first γGT risk estimation model and the second γGT risk estimation model. 
 
     
     
         10 . The γGT estimation device according to  claim 1 , further comprising a biological information estimation unit configured to estimate at least one piece or more of biological information among BMI, blood pressure, pulse wave data, electrocardiogram data, biological impedance, and oxygen saturation included in the biological information, wherein the information acquisition unit acquires, as biological information of the predetermined user, the biological information estimated by the biological information estimation unit. 
     
     
         11 . A non-invasive γGT estimation system comprising:
 the γGT estimation device according to  claim 1 ; and 
 a biological information measurement device configured to measure non-invasive biological information. 
 
     
     
         12 . A γGT estimation method comprising:
 a step of storing a training data set including attribute information, non-invasive biological information, and a blood-measured γGT measured value of a subject; 
 a step of generating a γGT estimation model by machine learning based on the training data set; and 
 a step of calculating a γGT estimated value of a predetermined user based on attribute information and/or non-invasive biological information of the predetermined user by using the γGT estimation model. 
 
     
     
         13 . A computer program configured to cause a computer to execute:
 a step of storing a training data set including attribute information, non-invasive biological information, and a blood-measured γGT measured value of a subject;   a step of generating a γGT estimation model by machine learning based on the training data set; and   a step of calculating a γGT estimated value of a predetermined user based on attribute information and/or non-invasive biological information of the predetermined user by using the γGT estimation model.